SPEC

A specification for configuring a framework that connects and coordinates several AI coding agents, including Claude, Codex, Gemini, and Jules.

In plain words
What is it for?
Use it when setting API keys, changing agent timeouts or logging, or checking the supported agent integrations. The listed required keys include credentials for Anthropic, OpenAI, and Gemini.
Why use it?
It documents required credentials, optional settings, defaults, and limits so agent operations can be configured consistently.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/docxology/codomyrmex/spec
Clone the repo
git clone --depth 1 https://github.com/docxology/codomyrmex
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00514
Opus 5 $0.00000 $0.00257
Sonnet 5 $0.00000 $0.00103
Haiku 4.5 $0.00000 $0.00051

Measured 2d ago against content hash 02543bf7354d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

SPEC scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

config/agents/SPEC.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agents Configuration Specification

Version: v1.1.9 | Status: Active | Last Updated: March 2026

Overview

AI agent framework integrations supporting 13 agentic frameworks including Claude, Codex, Gemini, Jules, and more. Provides API-based and CLI-based agent clients with orchestration. This specification documents the configuration schema and constraints.

Configuration Schema

Key Type Required Default Description
AGENT_DEFAULT_TIMEOUT string No 30 Default timeout in seconds for agent operations
AGENT_ENABLE_LOGGING string No true Enable or disable agent execution logging
ANTHROPIC_API_KEY string Yes None API key for Claude agent integration
OPENAI_API_KEY string Yes None API key for Codex/O1 agent integration
GEMINI_API_KEY string Yes None API key for Gemini agent integration

Environment Variables

# Required
export ANTHROPIC_API_KEY=""    # API key for Claude agent integration
export OPENAI_API_KEY=""    # API key for Codex/O1 agent integration
export GEMINI_API_KEY=""    # API key for Gemini agent integration

# Optional (defaults shown)
export AGENT_DEFAULT_TIMEOUT="30"    # Default timeout in seconds for agent operations
export AGENT_ENABLE_LOGGING="true"    # Enable or disable agent execution logging

Design Principles

  • Centralized Config: All settings accessible via config_management module
  • Env-First: Environment variables take precedence over config file values
  • Explicit Defaults: All optional settings have documented defaults
  • Zero-Mock: No placeholder or fake configuration values in production

Constraints

  • ANTHROPIC_API_KEY must be set before module initialization
  • OPENAI_API_KEY must be set before module initialization
  • GEMINI_API_KEY must be set before module initialization
  • Configuration is validated on first use; invalid values raise explicit errors
  • No silent fallback to placeholder values

Read the full file on GitHub · 54 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 54 lines · 0 tokens per session scan A 02543bf7354d

Subscribe to this mod's changes

SPEC is an agent published in the GitHub repository docxology/codomyrmex (11 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 514 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.